AI RESEARCH
Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning
arXiv CS.CV
•
ArXi:2605.04425v1 Announce Type: new Vision-language models such as CLIP achieve strong visual-textual alignment, but often suffer from overfitting and limited interpretability when adapted through continuous prompt learning. While discrete prompt optimization improves interpretability, it usually depends on large external models, leading to high computational costs and limited scalability. In this paper, we propose Interpretable Prompt Learning (IPL), a hybrid framework that alternates between discrete semantic token selection and continuous prompt optimization.